wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to incorporate language and context from
CONTEXT.mdandCONTEXT-MAP.mdlocated in the repository. - Ingestion points: Accesses
CONTEXT.mdandCONTEXT-MAP.mdfrom the workspace. - Boundary markers: Absent; the prompt does not provide delimiters or instructions to the agent to disregard potential commands embedded within the ingested files.
- Capability inventory: The skill does not define specific tool calls or subprocess executions, though it influences the agent's textual output.
- Sanitization: Absent; no validation or filtering of the file contents is performed before processing.
Audit Metadata